Menu

Not in the top 1,000 by GitHub stars

lllllllama/RigorPilot-Skills

README-first research reproduction skills with bounded execution, auditable evidence, and byte-preserving README annotations.

Claude CodeCodexDocumentationResearchEducation

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

skills/ai-research-explore/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

fb3ccdf5aa64 → fb3ccdf5aa64

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → fb3ccdf5aa64

No earlier version was observed for comparison.

Compare on GitHub

skills/ai-research-reproduction/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

fb3ccdf5aa64 → fb3ccdf5aa64

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → fb3ccdf5aa64

No earlier version was observed for comparison.

Compare on GitHub

skills/analyze-project/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Local scripts → After Local scripts

fb3ccdf5aa64 → fb3ccdf5aa64

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → fb3ccdf5aa64

No earlier version was observed for comparison.

Compare on GitHub

skills/env-and-assets-bootstrap/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Local scripts → After Local scripts

fb3ccdf5aa64 → fb3ccdf5aa64

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → fb3ccdf5aa64

No earlier version was observed for comparison.

Compare on GitHub

skills/explore-code/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Local scripts → After Local scripts

fb3ccdf5aa64 → fb3ccdf5aa64

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → fb3ccdf5aa64

No earlier version was observed for comparison.

Compare on GitHub

skills/explore-run/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Local scripts → After Local scripts

fb3ccdf5aa64 → fb3ccdf5aa64

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → fb3ccdf5aa64

No earlier version was observed for comparison.

Compare on GitHub

skills/minimal-run-and-audit/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Local scripts → After Local scripts

fb3ccdf5aa64 → fb3ccdf5aa64

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → fb3ccdf5aa64

No earlier version was observed for comparison.

Compare on GitHub

skills/paper-context-resolver/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

fb3ccdf5aa64 → fb3ccdf5aa64

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → fb3ccdf5aa64

No earlier version was observed for comparison.

Compare on GitHub

skills/repo-intake-and-plan/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

fb3ccdf5aa64 → fb3ccdf5aa64

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → fb3ccdf5aa64

No earlier version was observed for comparison.

Compare on GitHub

skills/run-train/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Local scripts → After Local scripts

fb3ccdf5aa64 → fb3ccdf5aa64

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → fb3ccdf5aa64

No earlier version was observed for comparison.

Compare on GitHub

skills/safe-debug/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Local scripts → After Local scripts

fb3ccdf5aa64 → fb3ccdf5aa64

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → fb3ccdf5aa64

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit fb3ccdf5aa64b1fa5b1d0463e666a8bc8bc26e01

git clone --filter=blob:none --no-checkout https://github.com/lllllllama/RigorPilot-Skills.git .hotskills/lllllllama-rigorpilot-skills && git -C .hotskills/lllllllama-rigorpilot-skills checkout --detach fb3ccdf5aa64b1fa5b1d0463e666a8bc8bc26e01 # Copy each selected skill directory from .hotskills/lllllllama-rigorpilot-skills into .claude/skills/<skill-name>/
git clone --filter=blob:none --no-checkout https://github.com/lllllllama/RigorPilot-Skills.git .hotskills/lllllllama-rigorpilot-skills && git -C .hotskills/lllllllama-rigorpilot-skills checkout --detach fb3ccdf5aa64b1fa5b1d0463e666a8bc8bc26e01 # Copy each selected skill directory from .hotskills/lllllllama-rigorpilot-skills into .agents/skills/<skill-name>/
486GitHub stars
0stars in 7 days
11skills in this repository
0commits in 30 days

Heat

0.3
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Nov 5, 2026486

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

ai-research-explore

When your agent uses it

Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates. Use when the researcher has chosen the task family, dataset, benchmark, evaluation method, provided SOTA references, and wants candidate-only exploration on top of `current_research` with auditable repo understanding, idea gating, fair comparison, and governed experiments written to `explore_outputs/`. Do not use for README-first trusted reproduction, open-ended direction finding, narrow code-only or run-only exploration, passive repo analysis, verified novelty claims, or implicit experimentation.

What it loads into context

Frontmatter

118 tokens

Always available to the agent

SKILL.md

1,430 tokens

When the skill is activated

Reference documents

7,795 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Purpose
  2. Fit
  3. Research Rhythm
  4. Workflow
  5. Ranking and Evidence
  6. Campaign Inputs
  7. Reference Loading

Scripts executed separately

  • scripts/lookup/__init__.py
  • scripts/lookup/cache_store.py
  • scripts/lookup/inventory_writer.py
  • scripts/lookup/normalizers.py
  • scripts/lookup/providers/__init__.py
  • scripts/lookup/providers/arxiv_provider.py
  • scripts/lookup/providers/base.py
  • scripts/lookup/providers/doi_provider.py
  • scripts/lookup/providers/github_provider.py
  • scripts/lookup/providers/optional_provider.py
  • scripts/lookup/providers/url_provider.py
  • scripts/lookup/record_schema.py
  • scripts/lookup/repo_extractors.py
  • scripts/lookup/source_support.py
  • scripts/orchestrate_explore.py
  • scripts/passes/__init__.py
  • scripts/passes/atomic_idea_decomposition.py
  • scripts/passes/candidate_idea_generation.py
  • scripts/passes/execution_feasibility.py
  • scripts/passes/idea_cards.py
  • scripts/passes/idea_ranking.py
  • scripts/passes/implementation_fidelity.py
  • scripts/passes/improvement_bank.py
  • scripts/passes/lookup_sources.py
  • scripts/passes/source_mapping.py
  • scripts/write_outputs.py

Files

  • SKILL.mdcore6,701 bytes
  • SKILL.mdcore6,701 bytes
  • SKILL.mdcore6,701 bytes
  • SKILL.mdcore6,701 bytes
  • agents/openai.yamlasset423 bytes
  • references/ai-research-explore-policy.mddoc1,803 bytes
  • references/idea-evaluation-framework.mddoc1,117 bytes
  • references/research-campaign-spec.mddoc9,663 bytes
  • references/smoke-validation-policy.mddoc787 bytes
  • references/source-mapping-policy.mddoc615 bytes
  • references/sources-naming-policy.mddoc895 bytes
  • scripts/lookup/__init__.pyruns624 bytes
  • scripts/lookup/cache_store.pyruns8,607 bytes
  • scripts/lookup/inventory_writer.pyruns3,139 bytes
  • scripts/lookup/normalizers.pyruns4,907 bytes
  • scripts/lookup/providers/__init__.pyruns457 bytes
  • scripts/lookup/providers/arxiv_provider.pyruns2,864 bytes
  • scripts/lookup/providers/base.pyruns3,086 bytes
  • scripts/lookup/providers/doi_provider.pyruns2,828 bytes
  • scripts/lookup/providers/github_provider.pyruns3,382 bytes
  • scripts/lookup/providers/optional_provider.pyruns844 bytes
  • scripts/lookup/providers/url_provider.pyruns2,090 bytes
  • scripts/lookup/record_schema.pyruns3,445 bytes
  • scripts/lookup/repo_extractors.pyruns3,064 bytes
  • scripts/lookup/source_support.pyruns4,505 bytes
  • scripts/orchestrate_explore.pyruns124,846 bytes
  • scripts/passes/__init__.pyruns909 bytes
  • scripts/passes/atomic_idea_decomposition.pyruns12,815 bytes
  • scripts/passes/candidate_idea_generation.pyruns22,068 bytes
  • scripts/passes/execution_feasibility.pyruns19,961 bytes
  • scripts/passes/idea_cards.pyruns1,788 bytes
  • scripts/passes/idea_ranking.pyruns8,649 bytes
  • scripts/passes/implementation_fidelity.pyruns16,637 bytes
  • scripts/passes/improvement_bank.pyruns19,244 bytes
  • scripts/passes/lookup_sources.pyruns16,634 bytes
  • scripts/passes/source_mapping.pyruns19,584 bytes
  • scripts/write_outputs.pyruns1,194 bytes
  • ../ai-research-reproduction/references/agent-operating-principles.mddoc2,768 bytes
  • ../ai-research-reproduction/references/continuous-learning-policy.mddoc3,825 bytes
  • ../ai-research-reproduction/references/deep-learning-experiment-principles.mddoc2,077 bytes
  • ../ai-research-reproduction/references/explore-variant-spec.mddoc4,215 bytes
  • ../ai-research-reproduction/references/research-rigor-principles.mddoc3,754 bytes
  • ../ai-research-reproduction/references/research-thinking-loop.mddoc4,189 bytes
Read SKILL.md

# ai-research-explore

## Purpose

Use this as the Rigor Explore compatible skill slug after the researcher
explicitly authorizes candidate-only work on top of a durable
`current_research` anchor. The installed slug remains `ai-research-explore` for
compatibility. Rigor Explore is for meaningful and potentially novel deep
learning research candidates while preserving scientific rigor, comparability,
reproducibility, and auditable collaboration. Novelty and significance remain
hypotheses before literature contrast, ablation evidence, and fair comparison.
The skill does not promise autonomous discovery, global benchmark completeness,
novelty proof, or trusted reproduction success.
View the complete source on GitHub

Skills included

  • ai-research-explore
  • ai-research-reproduction
  • analyze-project
  • env-and-assets-bootstrap
  • explore-code
  • explore-run
  • minimal-run-and-audit
  • paper-context-resolver
  • repo-intake-and-plan
  • run-train
  • safe-debug

Repository facts

License
MIT
Created
Mar 30, 2026
Last pushed
Sep 23, 2026
Forks
19
Open issues
1
Project activity
Active

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 5, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 7 notes
  • skills/ai-research-explore/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/ai-research-explore/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/ai-research-explore/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/ai-research-reproduction/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/ai-research-reproduction/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/env-and-assets-bootstrap/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/paper-context-resolver/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 158 signals by file

skills/ai-research-explore/scripts/lookup/__init__.py

  • Executable scriptline 1
    Executable file

skills/ai-research-explore/scripts/lookup/cache_store.py

  • Executable scriptline 1
    Executable file

skills/ai-research-explore/scripts/lookup/inventory_writer.py

  • Executable scriptline 1
    Executable file

skills/ai-research-explore/scripts/lookup/normalizers.py

  • Executable scriptline 1
    Executable file
  • Network accessline 41
    return text     if text.lower().startswith("doi:"):         return f"https://doi.org/{text[4:].strip()}"
  • Network accessline 42
    if text.lower().startswith("doi:"):         return f"https://doi.org/{text[4:].strip()}"     return text
  • Network accessline 43
    return f"https://doi.org/{text[4:].strip()}"
  • Network accessline 86
    "identifier": arxiv_id,         "arxiv_id": arxiv_id,         "url": f"https://arxiv.org/abs/{arxiv_id}",
  • Network accessline 87
    "arxiv_id": arxiv_id,         "url": f"https://arxiv.org/abs/{arxiv_id}",     }
  • Network accessline 88
    "url": f"https://arxiv.org/abs/{arxiv_id}",
  • Network accessline 105
    "identifier": doi,         "doi": doi,         "url": f"https://doi.org/{doi}",
  • Network accessline 106
    "doi": doi,         "url": f"https://doi.org/{doi}",     }
  • Network accessline 107
    "url": f"https://doi.org/{doi}",
  • Network accessline 133
    "repo": repo,         "source_file": source_file,         "url": f"https://github.com/{owner}/{repo}",
  • Network accessline 134
    "source_file": source_file,         "url": f"https://github.com/{owner}/{repo}",     }
  • Network accessline 135
    "url": f"https://github.com/{owner}/{repo}",

skills/ai-research-explore/scripts/lookup/providers/__init__.py

  • Executable scriptline 1
    Executable file

skills/ai-research-explore/scripts/lookup/providers/arxiv_provider.py

  • Executable scriptline 1
    Executable file
  • Network accessline 34
    try:         payload = http_get(             f"https://export.arxiv.org/api/query?id_list={urllib.parse.quote(arxiv_id)}",
  • Network accessline 35
    payload = http_get(             f"https://export.arxiv.org/api/query?id_list={urllib.parse.quote(arxiv_id)}",             accept="application/atom+xml, text/xml;q=0.9",
  • Network accessline 36
    f"https://export.arxiv.org/api/query?id_list={urllib.parse.quote(arxiv_id)}",
  • Network accessline 38
    )         root = ET.fromstring(payload.decode("utf-8", errors="ignore"))         namespace = {"atom": "http://www.w3.org/2005/Atom"}
  • Network accessline 39
    root = ET.fromstring(payload.decode("utf-8", errors="ignore"))         namespace = {"atom": "http://www.w3.org/2005/Atom"}         entry = root.find("atom:entry", namespace)
  • Network accessline 40
    namespace = {"atom": "http://www.w3.org/2005/Atom"}

skills/ai-research-explore/scripts/lookup/providers/base.py

  • Executable scriptline 1
    Executable file
  • Network accessline 60
    def http_get(url: str, *, accept: str = "application/json, text/plain;q=0.9, text/html;q=0.8") -> bytes:     request = urllib.request.Request(
  • Network accessline 61
    request = urllib.request.Request(
  • Network accessline 66
    },     )     with urllib.request.urlopen(request, timeout=REQUEST_TIMEOUT_SECONDS) as response:
  • Network accessline 67
    )     with urllib.request.urlopen(request, timeout=REQUEST_TIMEOUT_SECONDS) as response:         return response.read()
  • Network accessline 68
    with urllib.request.urlopen(request, timeout=REQUEST_TIMEOUT_SECONDS) as response:

skills/ai-research-explore/scripts/lookup/providers/doi_provider.py

  • Executable scriptline 1
    Executable file
  • Network accessline 19
    "normalized_id": locator_info.get("normalized_id", f"doi:{doi}"),         "title": f"DOI:{doi}" if doi else "",         "url": locator_info.get("url", f"https://doi.org/{doi}" if doi else ""),
  • Network accessline 20
    "title": f"DOI:{doi}" if doi else "",         "url": locator_info.get("url", f"https://doi.org/{doi}" if doi else ""),         "authors": [],
  • Network accessline 21
    "url": locator_info.get("url", f"https://doi.org/{doi}" if doi else ""),
  • Network accessline 34
    try:         payload = http_get(             f"https://doi.org/{urllib.parse.quote(doi, safe='/')}",
  • Network accessline 35
    payload = http_get(             f"https://doi.org/{urllib.parse.quote(doi, safe='/')}",             accept="application/vnd.citationstyles.csl+json, application/json;q=0.9",
  • Network accessline 36
    f"https://doi.org/{urllib.parse.quote(doi, safe='/')}",

skills/ai-research-explore/scripts/lookup/providers/github_provider.py

  • Executable scriptline 1
    Executable file
  • Network accessline 21
    def _fetch_readme(owner: str, repo: str) -> Dict[str, Any]:     try:         payload = http_get_json(f"https://api.github.com/repos/{owner}/{repo}/readme")
  • Network accessline 22
    try:         payload = http_get_json(f"https://api.github.com/repos/{owner}/{repo}/readme")     except Exception:
  • Network accessline 23
    payload = http_get_json(f"https://api.github.com/repos/{owner}/{repo}/readme")
  • Possible obfuscationline 30
    decoded = base64.b64decode(str(content).encode("utf-8"), validate=False).decode("utf-8", errors="ignore")
  • Network accessline 65
    return record     try:         payload = http_get_json(f"https://api.github.com/repos/{owner}/{repo}")
  • Network accessline 66
    try:         payload = http_get_json(f"https://api.github.com/repos/{owner}/{repo}")         readme_meta = _fetch_readme(owner, repo)
  • Network accessline 67
    payload = http_get_json(f"https://api.github.com/repos/{owner}/{repo}")

skills/ai-research-explore/scripts/lookup/providers/optional_provider.py

  • Executable scriptline 1
    Executable file
  • Access to secretsline 10
    [Credential-related source omitted]
  • Access to secretsline 11
    [Credential-related source omitted]
  • Access to secretsline 12
    [Credential-related source omitted]
  • Access to secretsline 21
    [Credential-related source omitted]

skills/ai-research-explore/scripts/lookup/providers/url_provider.py

  • Executable scriptline 1
    Executable file

skills/ai-research-explore/scripts/lookup/record_schema.py

  • Executable scriptline 1
    Executable file

skills/ai-research-explore/scripts/lookup/repo_extractors.py

  • Executable scriptline 1
    Executable file

skills/ai-research-explore/scripts/lookup/source_support.py

  • Executable scriptline 1
    Executable file

skills/ai-research-explore/scripts/orchestrate_explore.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ai-research-explore/scripts/passes/__init__.py

  • Executable scriptline 1
    Executable file

skills/ai-research-explore/scripts/passes/atomic_idea_decomposition.py

  • Executable scriptline 1
    Executable file

skills/ai-research-explore/scripts/passes/candidate_idea_generation.py

  • Executable scriptline 1
    Executable file

skills/ai-research-explore/scripts/passes/execution_feasibility.py

  • Executable scriptline 1
    Executable file

skills/ai-research-explore/scripts/passes/idea_cards.py

  • Executable scriptline 1
    Executable file

skills/ai-research-explore/scripts/passes/idea_ranking.py

  • Executable scriptline 1
    Executable file

skills/ai-research-explore/scripts/passes/implementation_fidelity.py

  • Executable scriptline 1
    Executable file

skills/ai-research-explore/scripts/passes/improvement_bank.py

  • Executable scriptline 1
    Executable file

skills/ai-research-explore/scripts/passes/lookup_sources.py

  • Executable scriptline 1
    Executable file

skills/ai-research-explore/scripts/passes/source_mapping.py

  • Executable scriptline 1
    Executable file

skills/ai-research-explore/scripts/write_outputs.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ai-research-reproduction/_bundled/shared/scripts/agent_provider.py

  • Executable scriptline 1
    Executable file
  • Network accessline 4
    import json import http.client
  • Network accessline 5
    import http.client
  • Network accessline 33
    elif isinstance(error, TimeoutError):         code = "timeout"     elif isinstance(error, http.client.HTTPException):
  • Network accessline 34
    code = "timeout"     elif isinstance(error, http.client.HTTPException):         code = "invalid_response"
  • Network accessline 35
    elif isinstance(error, http.client.HTTPException):
  • Network accessline 75
    def complete(self, messages: list, system: str, tools: list, max_tokens: int, timeout: float) -> dict:         profile = self.profile         endpoint = str(profile.get("endpoint") or os.getenv("ANTHROPIC_BASE_URL") or "https://api.anthropi
  • Network accessline 76
    profile = self.profile         endpoint = str(profile.get("endpoint") or os.getenv("ANTHROPIC_BASE_URL") or "https://api.anthropic.com").rstrip("/")         parsed = urlsplit(endpoint)
  • Network accessline 77
    endpoint = str(profile.get("endpoint") or os.getenv("ANTHROPIC_BASE_URL") or "https://api.anthropic.com").rstrip("/")
  • Access to secretsline 83
    [Credential-related source omitted]
  • Network accessline 92
    payload = {"model": profile["model"], "system": system, "messages": messages,                    "tools": tools, "max_tokens": max_tokens, **self.parameters}         request = urllib.request.Request(url, data=json.dumps(payload).encode(), h
  • Network accessline 93
    "tools": tools, "max_tokens": max_tokens, **self.parameters}         request = urllib.request.Request(url, data=json.dumps(payload).encode(), headers=headers)         try:
  • Network accessline 94
    request = urllib.request.Request(url, data=json.dumps(payload).encode(), headers=headers)
  • Network accessline 102
    except urllib.error.URLError as exc:             raise transport_error(exc.reason) from None         except (OSError, http.client.HTTPException) as exc:
  • Network accessline 103
    raise transport_error(exc.reason) from None         except (OSError, http.client.HTTPException) as exc:             raise transport_error(exc) from None
  • Network accessline 104
    except (OSError, http.client.HTTPException) as exc:

skills/ai-research-reproduction/_bundled/shared/scripts/command_utils.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ai-research-reproduction/_bundled/shared/scripts/lessons_store.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Access to secretsline 42
    [Credential-related source omitted]
  • Access to secretsline 47
    [Credential-related source omitted]

skills/ai-research-reproduction/_bundled/shared/scripts/model_adapter.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Access to secretsline 16
    [Credential-related source omitted]

skills/ai-research-reproduction/_bundled/shared/scripts/resource_monitor.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ai-research-reproduction/_bundled/shared/scripts/runtime_runner.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Access to secretsline 519
    [Credential-related source omitted]

skills/ai-research-reproduction/_bundled/shared/scripts/task_queue.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ai-research-reproduction/_bundled/shared/scripts/write_explore_bundle.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ai-research-reproduction/_bundled/shared/scripts/write_run_bundle.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ai-research-reproduction/_bundled/skills/analyze-project/scripts/analyze_project.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ai-research-reproduction/_bundled/skills/env-and-assets-bootstrap/scripts/plan_setup.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ai-research-reproduction/_bundled/skills/env-and-assets-bootstrap/scripts/prepare_assets.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ai-research-reproduction/_bundled/skills/minimal-run-and-audit/scripts/write_outputs.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ai-research-reproduction/_bundled/skills/repo-intake-and-plan/scripts/extract_commands.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Network accessline 126
    "cd ", ) ASSET_PREFIXES = ("wget ", "curl ", "mkdir ", "tar ", "unzip ", "7z ", "aria2c ")
  • Network accessline 128
    ASSET_PREFIXES = ("wget ", "curl ", "mkdir ", "tar ", "unzip ", "7z ", "aria2c ")
  • Network accessline 189
    if re.search(r"[\\/].+\.(?:py|sh|bat)", candidate):         return True     if candidate.startswith(("cd ", "ls ", "mkdir ", "wget ", "curl ", "git ")):
  • Network accessline 190
    return True     if candidate.startswith(("cd ", "ls ", "mkdir ", "wget ", "curl ", "git ")):         return True
  • Network accessline 191
    if candidate.startswith(("cd ", "ls ", "mkdir ", "wget ", "curl ", "git ")):

skills/ai-research-reproduction/_bundled/skills/repo-intake-and-plan/scripts/scan_repo.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ai-research-reproduction/_bundled/skills/run-train/scripts/run_training.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ai-research-reproduction/_bundled/skills/run-train/scripts/write_outputs.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ai-research-reproduction/assets/model_profile.template.json

  • Access to secretsline 5
    [Credential-related source omitted]

skills/ai-research-reproduction/references/agent-runner.md

  • Network accessline 4
    The existing deterministic orchestrator remains available. No SDK installation is needed: the client uses Python's standard library. Protocol reference: https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview
  • Network accessline 6
    https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview
  • Access to secretsline 98
    [Credential-related source omitted]
  • Access to secretsline 105
    [Credential-related source omitted]
  • Network accessline 122
    fields are rejected before HTTP; `max_tokens` remains controlled by the task budget. Leave sampling settings absent unless the selected model supports them: the [Messages API](https://platform.claude.com/docs/en/api/messages/create)
  • Network accessline 123
    budget. Leave sampling settings absent unless the selected model supports them: the [Messages API](https://platform.claude.com/docs/en/api/messages/create) deprecates these controls for newer models. A local protocol test is not a
  • Network accessline 124
    the [Messages API](https://platform.claude.com/docs/en/api/messages/create)

skills/ai-research-reproduction/references/runtime-and-model-adapter.md

  • Network accessline 63
    "revision": "2026-09-01",   "capabilities": ["text", "tool_calling", "structured_output"],   "endpoint": "https://gateway.example/v1",
  • Network accessline 64
    "capabilities": ["text", "tool_calling", "structured_output"],   "endpoint": "https://gateway.example/v1",   "credential_env": "LAB_MODEL_API_KEY",
  • Network accessline 65
    "endpoint": "https://gateway.example/v1",
  • Access to secretsline 66
    [Credential-related source omitted]

skills/ai-research-reproduction/scripts/annotate_readme.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ai-research-reproduction/scripts/doctor.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ai-research-reproduction/scripts/orchestrate_repro.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Access to secretsline 105
    [Credential-related source omitted]
  • Network accessline 931
    "pip install ", "pip3 install ", "python -m pip install ", "python3 -m pip install ",     "uv pip install ", "poetry install ", "conda install ", "conda create ", "conda env create ",     "conda activate ", "git clone ", "wget ", "curl ", "
  • Network accessline 932
    "uv pip install ", "poetry install ", "conda install ", "conda create ", "conda env create ",     "conda activate ", "git clone ", "wget ", "curl ", "aria2c ", "make install ",     "npm install ", "npm ci ", "yarn install ", "pnpm install "
  • Network accessline 933
    "conda activate ", "git clone ", "wget ", "curl ", "aria2c ", "make install ",

skills/ai-research-reproduction/scripts/repro_job.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Access to secretsline 185
    [Credential-related source omitted]
  • Access to secretsline 251
    [Credential-related source omitted]

skills/ai-research-reproduction/scripts/run_agent.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Access to secretsline 65
    [Credential-related source omitted]
  • Access to secretsline 66
    [Credential-related source omitted]
  • Access to secretsline 77
    [Credential-related source omitted]
  • Network accessline 341
    if any(not isinstance(v, int) or isinstance(v, bool) or v <= 0 for v in budget.values()):         raise ValueError("All budget limits must be positive integers")     endpoint_identity = fingerprint(profile.get("endpoint") or os.getenv("ANTH
  • Network accessline 342
    raise ValueError("All budget limits must be positive integers")     endpoint_identity = fingerprint(profile.get("endpoint") or os.getenv("ANTHROPIC_BASE_URL") or "https://api.anthropic.com")     harness_identity = fingerprint([Path(__file__
  • Network accessline 343
    endpoint_identity = fingerprint(profile.get("endpoint") or os.getenv("ANTHROPIC_BASE_URL") or "https://api.anthropic.com")
  • Access to secretsline 469
    [Credential-related source omitted]

skills/analyze-project/scripts/analyze_project.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/env-and-assets-bootstrap/scripts/bootstrap_env.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/env-and-assets-bootstrap/scripts/bootstrap_env.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

skills/env-and-assets-bootstrap/scripts/plan_setup.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/env-and-assets-bootstrap/scripts/prepare_assets.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/explore-code/scripts/plan_code_changes.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/explore-code/scripts/write_outputs.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/explore-run/scripts/plan_variants.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/explore-run/scripts/write_outputs.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/minimal-run-and-audit/scripts/run_command.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/minimal-run-and-audit/scripts/write_outputs.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/repo-intake-and-plan/scripts/extract_commands.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Network accessline 126
    "cd ", ) ASSET_PREFIXES = ("wget ", "curl ", "mkdir ", "tar ", "unzip ", "7z ", "aria2c ")
  • Network accessline 128
    ASSET_PREFIXES = ("wget ", "curl ", "mkdir ", "tar ", "unzip ", "7z ", "aria2c ")
  • Network accessline 189
    if re.search(r"[\\/].+\.(?:py|sh|bat)", candidate):         return True     if candidate.startswith(("cd ", "ls ", "mkdir ", "wget ", "curl ", "git ")):
  • Network accessline 190
    return True     if candidate.startswith(("cd ", "ls ", "mkdir ", "wget ", "curl ", "git ")):         return True
  • Network accessline 191
    if candidate.startswith(("cd ", "ls ", "mkdir ", "wget ", "curl ", "git ")):

skills/repo-intake-and-plan/scripts/scan_repo.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/run-train/scripts/run_training.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/run-train/scripts/write_outputs.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/safe-debug/scripts/safe_debug.py

  • Executable scriptline 1
    #!/usr/bin/env python3

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Declared and executed: 9 facts
Signal confidence: 157 facts

and 107 more

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativePath .claude/commands/ai-research-explore.md.claude/skills/<skill-name>/
CodexNativeManifest AGENTS.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skills/ai-research-explore/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skills/ai-research-explore/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skills/ai-research-explore/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skills/ai-research-explore/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

sandbaseai/sandbase-skills

88 installable open-source Agent Skills for research, social intelligence, marketing, and business workflows—compatible with Codex, Claude Code, Cursor, Gemini CLI, and DeepSeek H…

207GitHub stars

ShaishavMaisuria/research-paper-lifecycle-skills

42 AI agent skills for literature review, academic writing, citation verification, conference submission, rebuttal, publication, and presentations.

60GitHub stars

K-Dense-AI/drug-discovery-agent-skills

Agent Skills for small-molecule and protein therapeutics: cheminformatics, molecular ML, docking and dynamics, protein design platforms, and target-discovery knowledge graphs.

54GitHub stars

matkumatmat/very-deep-search

Agent skill: multi-agent gather-and-verify pipeline for deep literature search — 20 sources, two-layer verification with saved evidence, relevance scoring.

17GitHub stars

MisterBrookT/zeroplot

Plot anything with zero effort. Editable charts, diagrams, figures, posters, and slides.

11GitHub stars

josueazc/academic-writing-kit

Turn ideas into structured academic work: an AI-ready knowledge base with APA 7 guidance, source discovery, reference checks, rubric reviews, and Markdown-to-Word tools. Pure Pyth…

7GitHub stars